hydrodata.model_evaluation.evaluation_metrics module

Evaluation Metrics

• Root Mean Square Error (RMSE)

• Pearson Correlation Coefficient (R)

• Spearman’s Rank Correlation Coefficient

• Nash-Sutcliffe Efficiency (NSE)

• Kling-Gupta Efficiency (KGE)

• Correlation of determination (R2)

• Bias from R

• Percent Bias

hydrodata.model_evaluation.evaluation_metrics.KGE(x, y)

Calculate Kling-Gupta Efficiency (KGE).

Refer to Equation 9 in https://doi.org/10.1016/j.jhydrol.2009.08.003.

Parameters:

• x (array-like of shape (n_samples,)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.NSE(x, y)

Calculate Nash-Sutcliffe Efficiency (NSE).

Refer to https://doi.org/10.1016/0022-1694(70)90255-6.

Parameters:

• x (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.RMSE(x, y)

Calculate RMSE.

Refer to https://scikit-learn.org/stable/modules/generated/sklearn.metrics.mean_squared_error.html.

Parameters:

• x (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.R_squared(x, y)

Calculate R**2.

Refer to https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html.

Parameters:

• x (array-like of shape (n_samples,)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.bias_from_R(x, y)

Calculate the bias from R.

The bias from R indicates systematic additive and multiplicative biases in the generated values, with a value between 0 and 1, where bias = 1 means no bias. Refer to Equation 16 on the paper (https://www.nature.com/articles/srep19401).

Parameters:

• x (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.pearson_R(x, y)

Calculate Pearson’s R.

Refer to https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.pearsonr.html.

Parameters:

• x (array-like of shape (n_samples,)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.percent_bias(x, y)

Calculate percent bias.

Parameters:

• x (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,) or (n_samples, n_outputs)) – Estimated values.

Return type:

float or ndarray of floats

hydrodata.model_evaluation.evaluation_metrics.spearman_rank(x, y)

Calculate Spearman’s Rank Correlation Coefficient.

Refer to https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.spearmanr.html.

Parameters:

• x (array-like of shape (n_samples,)) – Ground Truth (correct) target values.

• y (array-like of shape (n_samples,)) – Estimated values.

Return type:

float or ndarray of floats